Biography
Vieri Giuliano Santucci received the B.Sc. degree in philosophy from the University of Pisa, Italy, and the M.S. degree in theories and techniques of knowledge from the Faculty of Philosophy, University of Rome “La Sapienza,” Italy. He holds a Ph.D. in computer science from the University of Plymouth, U.K.. From 2010 he is a Researcher with the Istituto di Scienze e Tecnologie della Cognizione (ISTC), Consiglio Nazionale delle Ricerche (CNR), Rome. He published in peer-reviewed journals and attended several international conferences, and actively contributed to the European Integrated Projects “IM-CLeVeR— Intrinsically-Motivated Cumulative-Learning Versatile Robots.” and “GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots” where he focussed on the development of robotic architectures that allow artificial agents to autonomously improve their competences on the basis of the biologically-inspired concept of intrinsic motivations. His current research interests include the study of learning and motivational processes, both in artificial and biological agents.
Abstract
From GRAIL to M-GRAIL: Autonomous open-ended learning of interdependent tasks
Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning. Intrinsic motivations have proven to properly generate a task-agnostic signal to drive the autonomous acquisition of multiple policies in settings requiring the learning of multiple tasks. However, in real-world scenarios tasks may be interdependent so that some of them may constitute the precondition for learning other ones. Despite different strategies have been used to tackle the acquisition of interdependent/hierarchical tasks, fully autonomous open-ended learning in these scenarios is still an open question. Building on previous research within the framework of intrinsically-motivated open-ended learning, we present here M-GRAIL, an architecture for robot control that tackles this problem from the point of view of decision making, i.e. treating the selection of tasks as a Markov Decision Process where the system selects the policies to be trained in order to maximise its competence over all the tasks.
